Article

Overlooked features lead to divergent neurobiological interpretations of brain-based machine learning biomarkers

2025-03-13

Abstract excerpt

A central objective in human neuroimaging is to understand the neurobiology underlying cognition and mental health. Machine learning models trained on brain connectivity data are increasingly used as tools for predicting behavioral phenotypes 1,2, enhancing precision medicine 3,4, and improving generalizability compared to traditional MRI studies 5. However, the high dimensionality of brain connectivity data makes...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 7d63e49c-d5bd-5299-8871-c12b76f1892b
DOI: 10.1101/2025.03.12.642878

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Overlooked features lead to divergent neurobiological interpretations of brain-based machine learning biomarkersDOI 10.1101/2025.03.12.642878Read

Brain-phenotype predictions can survive across diverse real-world dataSemantic proximity Read

Scaling up: Brain-based psychometric assessments target functional networks across psychiatric disordersSemantic proximity Read

Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomesSemantic proximity Read

Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and PromisesSemantic proximity Read

Computational Mechanisms of Neuroimaging Biomarkers Uncovered by Multicenter Resting-State fMRI Connectivity Variation ProfileSemantic proximity Read

Relationships between Human Brain Structural Connectomes and TraitsSemantic proximity Read

Deep Neural Networks and Kernel Regression Achieve Comparable Accuracies for Functional Connectivity Prediction of Behavior and DemographicsSemantic proximity Read

Task-Based Functional Connectomes Predict Cognitive Phenotypes Across Psychiatric DiseaseSemantic proximity Read

Delineating Transdiagnostic Subtypes in Neurodevelopmental Disorders via Contrastive Graph Machine Learning of Brain Connectivity PatternsSemantic proximity Read

Phenotype Prediction Using BEN-Based Predictive Modeling (BPM)Semantic proximity Read

The Transdiagnostic Connectome Project: a richly phenotyped open dataset for advancing the study of brain-behavior relationships in psychiatrySemantic proximity Read

Neuropredictome: a data-driven predictome for cognitive, psychiatric, medical, and lifestyle factors on the brainSemantic proximity Read